Syntology converts AI/ML research into a structured, provenance-tagged graph — papers, citations, methods, and code, indexed so the distance between publication and implementation gets smaller. There's no team page here because there's no team yet: one founder, a verifiable background, and links below to check it directly.
Engineering physicist (B.S., Engineering Physics, Colorado School of Mines, cum laude) who spent the past decade building signal-processing and machine-learning systems for atmospheric remote sensing — calibration, retrieval algorithms, and command-and-data software for ground-based radiometers at Radiometrics; NASA Phase A programs on next-generation atmospheric observation hardware at Orbital Micro Systems and Weather Stream (the Atmospheric Observing System and the Sounder for Microwave-Based Applications); and two ventures of his own, Boundary Conditions and now Syntology.
The direction traces back to 2014 — an MIT internship taken during a physics PhD track. The internship didn't lead to a PhD, but it showed what a functioning research community looks like from the inside: papers, conferences, and the slow, uneven process of getting an idea out of a lab and into general use. Syntology is an attempt to compress that process — a structured, provenance-tagged graph of AI/ML research meant to be a public resource, not something built to sit behind the research it indexes.